Goto

Collaborating Authors

 joubert


AI Weekly: The promise and limitations of machine programming tools

#artificialintelligence

Machine programming, which automates the development and maintenance of software, is becoming supercharged by AI. During its Build developer conference in May, Microsoft detailed a new feature in Power Apps that taps OpenAI's GPT-3 language model to assist people in choosing formulas. Intel's ControlFlag can autonomously detect errors in code. And Facebook's TransCoder converts code from one programming language into another. The applications of computer programming are vast in scope.


Artificial intelligence platform helps developers spend less time on unit tests, bug fixes, documentation

#artificialintelligence

Developers spend around half of their time on tasks other than coding, and French startup Ponicode is looking to change that with a little help from artificial intelligence. The company, which was founded in June 2019, has created a platform embedded with AI that learns from millions of lines of code. The Ponicode platform allows developers to write unit tests directly in the editor to help decrease the number of bugs at the production stage, according to Ponicode CEO and co-founder Patrick Joubert. Coding has not changed in the past 30 years and while developers might have more libraries and tools at their disposal, "In the end, the quality of our code still only depends on our personal judgment and experience," Joubert said. "Our goal is to help developers focus on what they like to do most: coding," he said.